← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
1k
tokens
353.2
PP tok/s
16.9
TG tok/s
2900
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip
M5 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.3.8
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 353.2 | 16.9 | 16.4 GB | current |
| 4k | 383.7 | 14.8 | 17.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 16.9 | 1.00× |
| 2× | 23.7 | 1.40× |
| 4× | 25.1 | 1.49× |